Questions tagged [neural-computing]
The neural-computing tag has no summary.
21 questions
1
vote
0
answers
44
views
NEAT (Neuroevolution): are innovation numbers needed?
This is related to this question: NeuroEvolution: NEAT algorithm innovation numbers
However, I am still struggling to understand why innovation numbers are useful in the first place? As I understand ...
- 111
-2
votes
1
answer
91
views
How could "the mind" be uncomputable if it's due to neurons processing information?
This is going to be a very naïve question:
Some biologists, physicists and computer scientists say that what our brain does (generally speaking "the mind", including our thoughts, our ...
- 105
1
vote
0
answers
63
views
In theory, should neuromorphic computers be more efficient than traditional computers when performing logic?
There is this general sentiment about neuromorphic computers that they are simply "more efficient" than von Neuman.
I've heard a lot of talk about neuromorphic computers in the context of ...
- 111
0
votes
0
answers
101
views
Delta rule for binary step function
I have a question of understanding about the Delta Rule:
$\Delta w_i = (y - \hat{y}) \times x_i$
Why does $x$ have to be multiplied again after the difference? If the input is $0$, the product of $w$...
- 101
0
votes
1
answer
56
views
Intersection of two generative neural networks
I have an input x (a word), and I have a neural network Y such that Y(x), which is an image always satisfies F(x), and another neural network Z such that Z(x), which is also an image, always satisfies ...
- 225
0
votes
1
answer
58
views
Using a point as an input for a perceptron
Can a point be used as the input for a perceptron/neural net?
The relationship between the two numbers that make up a 2D point does not affect the output, but does this not matter when the ...
-1
votes
1
answer
241
views
If the human brain is a Turing machine then how is it able to ascertain that certain problems are undecidable? [closed]
I recently read about the idea that the human brain might be a Turing machine (or Turing complete). If that is true then how is the brain able to reason that a certain problem is undecidable for e.g. ...
0
votes
1
answer
2k
views
Single Layer Perceptron vs Multi Layer Perceptron
Why the single layer perceptron has a linear activation function while the Multi Layer Perceptron has a non-linear activation function ?
What is the potential of the Multi Layer Perceptron respect of ...
- 133
4
votes
1
answer
1k
views
Analog circuits for neural networks?
Neural networks in machine learning are inherently a continuous model of computation. Yet we use digital logic circuits with floating point numbers to "emulate" this continuity.
I am wondering: is ...
- 277
1
vote
1
answer
527
views
Is deep learning appropriate to approximate dynamic programming problems?
I have a problem which can be completely solved using dynamic programming, but in a very intractable way (On^4, where n is around 1000). I won't get into the details of the problem since it's a bit ...
- 225
0
votes
0
answers
196
views
Replace EKF by Neural Networks
I made a SLAM (Simultaneous Localization And Mapping) using Extended Kalman Filter (EKF) and it works really good, but I want to see if it works better using Neural Networks.
For the EKF I used an ...
- 101
0
votes
1
answer
135
views
Is it Possible to Get Maximum Weighted Input Value in a Neural Network?
Let's say that I have a standard feedforward neural network which has $M$ inputs, some number of hidden layers $N$, and a single neuron in the output.
Is it possible to construct a network such that ...
- 1,368
3
votes
1
answer
1k
views
NeuroEvolution: NEAT algorithm innovation numbers
I have been reading up on the NeuronEvolution of Augmented Topologies and there's this little thing that's been bothering me. While reading Kenneth Stanley's Paper on NEAT I came on this figure here:
...
- 133
2
votes
1
answer
85
views
How to model a set of categorical values in the input of a neural network
One of the inputs to my neural network is a set. I have a set $S = \{s_0, s_1, ..., s_n\}$ in which all values $s_i$ are constant. An example of such a set could be the set of French wines (...
- 1,100
0
votes
1
answer
418
views
Architecture of a chatbot - how to organize and fetch possibilities? [closed]
I'm building a chatbot that would respond to text messages.
Let's say that my chatbot works for customers of an internet provider and it can respond to the following things:
Problems:
About payment;
...
- 101